Collective Learning for Unified Robotic Manipulation via Predictive Dynamics Adaptation

Summary

Learning a collective policy for state-based Cartesian manipulation across diverse robotic embodiments presents a fundamental challenge due to embodiment-dependent transition dynamics.

Abstract Summary

Learning a collective policy for state-based Cartesian manipulation across diverse robotic embodiments presents a fundamental challenge due to embodiment-dependent transition dynamics. Collective learning aggregates multi-robot experience to discover shared task structure, yet naive aggregation can average incompatible action modes when different embodiments realize the same Cartesian command through different transition behavior. This leads to strategy ambiguity and performance collapse on dynamically outlying embodiments. To address this, we propose PACE, a two-stage collective learning framework that separates shared task-space intent from embodiment-dependent transition dynamics. The first stage employs a representation layer pre-trained on offline trajectories to extract task-level context from collective data. The second stage introduces a decision layer equipped with a predictive dynamics adapter. By forcing the latent state to predict future transitions, this adapter acts as a latent regularizer that grounds the policy in the transition behavior of the executing robot while preserving real-time inference without online planning. Evaluations across simulated embodiments demonstrate that our method prevents performance collapse on distinct robots. It achieves over 93\% overall success and 89\% on dynamically out-of-distribution zero-shot simulated robots, outperforming the Transformer behavior cloning (82\%) and diffusion policy baselines (66\%). Physical KUKA deployment further validates the feasibility of the full state-based pipeline under zero-shot sim-to-real transfer.

Key Points

Learning a collective policy for state-based Cartesian manipulation across diverse robotic embodiments presents a fundamental challenge due to embodiment-dependent transition dynamics.
Collective learning aggregates multi-robot experience to discover shared task structure, yet naive aggregation can average incompatible action modes when different embodiments realize the same Cartesian command through different transition behavior.
This leads to strategy ambiguity and performance collapse on dynamically outlying embodiments
To address this, we propose PACE, a two-stage collective learning framework that separates shared task-space intent from embodiment-dependent transition dynamics.
The first stage employs a representation layer pre-trained on offline trajectories to extract task-level context from collective data.

Methodology

We formulate collective multi-task imitation learning as a family of Markov Decision Processes (MDPs), $\mathcal{M}=\{M_{rob,task}\mid rob\in\mathcal{R},\tau\in\mathcal{T}\}$, where $\mathcal{R}$ represents distinct robot embodiments and $\mathcal{T}$ represents manipulation tasks. Unified state and action spaces. We use a unified Cartesian space to facilitate transfer.

Experiments

This section evaluates whether PACE improves collective manipulation learning across robot embodiments with different transition behavior. We use a shared low-dimensional state representation and Cartesian action interface for all methods, so the comparison focuses on embodiment-dependent differences in how commanded actions are realized.

Preliminary observations highlight a critical limitation in standard Behavior Cloning baselines.

Experiments — Collective Learning for Unified Robotic Manipulation via Predictive Dynamics Adaptation — Fig. 2 : Structure of PACE. The two-stage distillation framework features 1. an offline representation layer with a trajectory transformer encoder, and 2. an online decision layer with a predictive dynamics adapter and collective agent policy.

Sources and Demonstrations

Figures are reproduced from Liu et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.